{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T13:18:22Z","timestamp":1778246302773,"version":"3.51.4"},"reference-count":34,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","jvoice.org","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Voice"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.jvoice.2026.03.041","type":"journal-article","created":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T12:45:18Z","timestamp":1778244318000},"update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automatic Classification of Functional Dysphonia Using Voc2Vec Speech Representations"],"prefix":"10.1016","author":[{"given":"Kiran Reddy","family":"Mittapalle","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvoice.2026.03.041_bib1","doi-asserted-by":"crossref","first-page":"243","DOI":"10.2147\/PROM.S68631","article-title":"Functional dysphonia: strategies to improve patient outcomes","volume":"6","author":"Behlau","year":"2015","journal-title":"Patient Relat Outcome Meas"},{"key":"10.1016\/j.jvoice.2026.03.041_bib2","series-title":"Understanding Voice Problems; A Physiological Perspective for Diagnosis and Treatment","author":"Reymond","year":"2006"},{"key":"10.1016\/j.jvoice.2026.03.041_bib3","first-page":"169","article-title":"Etiologies of dysphonia in patients referred to ENT clinics based on videolaryngoscopy","volume":"26","author":"Kiakojoury","year":"2014","journal-title":"Iran J Otorhinolaryngol"},{"key":"10.1016\/j.jvoice.2026.03.041_bib4","first-page":"656","article-title":"Vocal therapy of hyperkinetic dysphonia","volume":"142","author":"Mumovi\u0107","year":"2014","journal-title":"Serbian Arch Med"},{"key":"10.1016\/j.jvoice.2026.03.041_bib5","doi-asserted-by":"crossref","first-page":"761.e1","DOI":"10.1016\/j.jvoice.2015.09.017","article-title":"Voice disorders: etiology and diagnosis","volume":"30","author":"Martins","year":"2015","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2026.03.041_bib6","doi-asserted-by":"crossref","first-page":"67745","DOI":"10.1109\/ACCESS.2020.2986171","article-title":"Glottal source information for pathological voice detection","volume":"8","author":"Narendra","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvoice.2026.03.041_bib7","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1109\/JSTSP.2019.2957988","article-title":"Analysis and detection of pathological voice using glottal source features","volume":"14","author":"Kadiri","year":"2019","journal-title":"IEEE J Sel Top Signal Process"},{"key":"10.1016\/j.jvoice.2026.03.041_bib8","doi-asserted-by":"crossref","first-page":"101205","DOI":"10.1016\/j.csl.2021.101205","article-title":"The automatic detection of heart failure using speech signals","volume":"69","author":"Reddy","year":"2021","journal-title":"Comput Speech Lang"},{"key":"10.1016\/j.jvoice.2026.03.041_bib9","doi-asserted-by":"crossref","first-page":"135953","DOI":"10.1109\/ACCESS.2021.3117665","article-title":"A comparison of cepstral features in the detection of pathological voices by varying the input and filterbank of the cepstrum computation","volume":"4","author":"Reddy","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvoice.2026.03.041_bib10","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1109\/TASLP.2022.3212829","article-title":"Automatic assessment of Parkinson\u2019s disease using speech representations of phonation and articulation","volume":"31","author":"Liu","year":"2023","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"10.1016\/j.jvoice.2026.03.041_bib11","doi-asserted-by":"crossref","first-page":"1863","DOI":"10.1109\/LSP.2022.3199669","article-title":"End-to-end pathological speech detection using wavelet scattering network","volume":"29","author":"Reddy","year":"2022","journal-title":"IEEE Signal Process Lett"},{"key":"10.1016\/j.jvoice.2026.03.041_bib12","doi-asserted-by":"crossref","first-page":"1386","DOI":"10.1109\/TASLP.2023.3260709","article-title":"Exemplar-based sparse representations for detection of Parkinson\u2019s disease from speech","volume":"31","author":"Reddy","year":"2023","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"10.1016\/j.jvoice.2026.03.041_bib13","doi-asserted-by":"crossref","first-page":"15273","DOI":"10.1109\/ACCESS.2020.2967224","article-title":"Detection of specific language impairment in children using glottal source features","volume":"8","author":"Reddy","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvoice.2026.03.041_bib14","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1109\/OJSP.2023.3242862","article-title":"Hierarchical multi-class classification of voice disorders using self-supervised models and glottal features","volume":"4","author":"Tirronen","year":"2023","journal-title":"IEEE Open J Signal Process"},{"key":"10.1016\/j.jvoice.2026.03.041_bib15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2009\/567875","article-title":"Jitter estimation algorithms for detection of pathological voices","volume":"2009","author":"Silva","year":"2009","journal-title":"EURASIP J Adv Signal Process"},{"key":"10.1016\/j.jvoice.2026.03.041_bib16","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1159\/000219951","article-title":"Voice pathology detection based on short term jitter estimations in running speech","volume":"61","author":"Vasilakis","year":"2009","journal-title":"Folia Phoniatr Logop"},{"key":"10.1016\/j.jvoice.2026.03.041_bib17","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1016\/j.jvoice.2004.11.005","article-title":"Perturbation and nonlinear dynamic analyses of voices from patients with unilateral laryngeal paralysis","volume":"19","author":"Zhang","year":"2005","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2026.03.041_bib18","doi-asserted-by":"crossref","first-page":"5196","DOI":"10.3390\/s23115196","article-title":"An experimental analysis on multicepstral projection representation strategies for dysphonia detection","volume":"23","author":"Contreras","year":"2023","journal-title":"Sensors"},{"key":"10.1016\/j.jvoice.2026.03.041_bib19","unstructured":"Osma-Ruiz, V, Fraile R, Godino-Llorente JI, et al. Spectral analysis of pathological voices: sustained vowels vs running speech. Proceedings of the Seventh International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications; 2011."},{"key":"10.1016\/j.jvoice.2026.03.041_bib20","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1109\/ACCESS.2020.3046767","article-title":"Investigation and evaluation of glottal flow waveform for voice pathology detection","volume":"9","author":"Wu","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvoice.2026.03.041_bib21","doi-asserted-by":"crossref","DOI":"10.1016\/j.specom.2023.102989","article-title":"Classification of functional dysphonia using the tunable Q wavelet transform","volume":"155","author":"Mittapalle","year":"2023","journal-title":"Speech Commun"},{"key":"10.1016\/j.jvoice.2026.03.041_bib22","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvoice.2024.11.016","article-title":"Tunable Q-factor wavelet transform-based features in the classification of phonation types in the singing and speaking voice","author":"Mittapalle","year":"2024","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2026.03.041_bib23","doi-asserted-by":"crossref","first-page":"370","DOI":"10.1109\/TBME.2010.2089052","article-title":"Automatic detection of pathological voices using complexity measures, noise parameters, and mel-cepstral coefficients","volume":"58","author":"Arias-Londo\u00f1o","year":"2011","journal-title":"IEEE Trans Biomed Eng"},{"key":"10.1016\/j.jvoice.2026.03.041_bib24","doi-asserted-by":"crossref","first-page":"3595","DOI":"10.3390\/e17063595","article-title":"Entropies from Markov models as complexity measures of embedded attractors","volume":"17","author":"Arias-Londo\u00f1o","year":"2015","journal-title":"Entropy"},{"key":"10.1016\/j.jvoice.2026.03.041_bib25","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1109\/TAFFC.2015.2457417","article-title":"The Geneva minimalistic acoustic parameter set (GeMAPS) for voice research and affective computing","volume":"7","author":"Eyben","year":"2015","journal-title":"IEEE Trans Affect Comput"},{"key":"10.1016\/j.jvoice.2026.03.041_bib26","series-title":"The INTERSPEECH 2010 paralinguistic challenge","first-page":"2794","author":"Schuller","year":"2010"},{"key":"10.1016\/j.jvoice.2026.03.041_bib27","unstructured":"Baevski A, Zhou Y, Mohamed A, et al. wav2vec 2.0: a framework for self-supervised learning of speech representations. Advances in neural information processing systems 2020;33:12449\u201312460."},{"key":"10.1016\/j.jvoice.2026.03.041_bib28","doi-asserted-by":"crossref","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","article-title":"Hubert: self-supervised speech representation learning by masked prediction of hidden units","volume":"29","author":"Hsu","year":"2021","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"10.1016\/j.jvoice.2026.03.041_bib29","doi-asserted-by":"crossref","DOI":"10.1016\/j.specom.2026.103355","article-title":"Classification of phonation types in singing and speaking voice using self-supervised learning models","volume":"178","author":"Patil","year":"2026","journal-title":"Speech Commun"},{"key":"10.1016\/j.jvoice.2026.03.041_bib30","doi-asserted-by":"crossref","unstructured":"Koudounas A, LaQuatra M, Siniscalchi SM, et al. voc2vec: a foundation model for non-verbal vocalization. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 2025:1\u20135.","DOI":"10.1109\/ICASSP49660.2025.10890672"},{"key":"10.1016\/j.jvoice.2026.03.041_bib31","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1016\/j.compeleceng.2018.04.008","article-title":"A new database of healthy and pathological voices","volume":"68","author":"Cesari","year":"2018","journal-title":"Comput Electr Eng"},{"key":"10.1016\/j.jvoice.2026.03.041_bib32","unstructured":"Verde L, Sannino G.VOICED database; 2018. Accessed on: 10\/Dec\/2025. Available at: \u3008https:\/\/physionet.org\/content\/voiced\/1.0.0\/\u3009."},{"key":"10.1016\/j.jvoice.2026.03.041_bib33","unstructured":"openSMILE 3.0.1 [online]. Accessed on: 10\/Dec\/2025. Available at: \u3008https:\/\/github.com\/audeering\/opensmile\/releases\u3009."},{"key":"10.1016\/j.jvoice.2026.03.041_bib34","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"Smote: synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J Artif Intell Res"}],"container-title":["Journal of Voice"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089219972600158X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089219972600158X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T12:45:31Z","timestamp":1778244331000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S089219972600158X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":34,"alternative-id":["S089219972600158X"],"URL":"https:\/\/doi.org\/10.1016\/j.jvoice.2026.03.041","relation":{},"ISSN":["0892-1997"],"issn-type":[{"value":"0892-1997","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Automatic Classification of Functional Dysphonia Using Voc2Vec Speech Representations","name":"articletitle","label":"Article Title"},{"value":"Journal of Voice","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvoice.2026.03.041","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Voice Foundation. Published by Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}]}}